Summary of the Data
head(data)
str(data)
## 'data.frame': 14999 obs. of 11 variables:
## $ ï..Emp_Id : chr "IND02438" "IND28133" "IND07164" "IND30478" ...
## $ satisfaction_level : chr "38%" "80%" "11%" "72%" ...
## $ last_evaluation : chr "53%" "86%" "88%" "87%" ...
## $ number_project : int 2 5 7 5 2 2 6 5 5 2 ...
## $ average_montly_hours : int 157 262 272 223 159 153 247 259 224 142 ...
## $ time_spend_company : int 3 6 4 5 3 3 4 5 5 3 ...
## $ Work_accident : int 0 0 0 0 0 0 0 0 0 0 ...
## $ left : int 1 1 1 1 1 1 1 1 1 1 ...
## $ promotion_last_5years: int 0 0 0 0 0 0 0 0 0 0 ...
## $ Department : chr "sales" "sales" "sales" "sales" ...
## $ salary : chr "low" "medium" "medium" "low" ...
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
glimpse(data)
## Rows: 14,999
## Columns: 11
## $ ï..Emp_Id <chr> "IND02438", "IND28133", "IND07164", "IND30478", ~
## $ satisfaction_level <chr> "38%", "80%", "11%", "72%", "37%", "41%", "10%",~
## $ last_evaluation <chr> "53%", "86%", "88%", "87%", "52%", "50%", "77%",~
## $ number_project <int> 2, 5, 7, 5, 2, 2, 6, 5, 5, 2, 2, 6, 4, 2, 2, 2, ~
## $ average_montly_hours <int> 157, 262, 272, 223, 159, 153, 247, 259, 224, 142~
## $ time_spend_company <int> 3, 6, 4, 5, 3, 3, 4, 5, 5, 3, 3, 4, 5, 3, 3, 3, ~
## $ Work_accident <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ~
## $ left <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ~
## $ promotion_last_5years <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ~
## $ Department <chr> "sales", "sales", "sales", "sales", "sales", "sa~
## $ salary <chr> "low", "medium", "medium", "low", "low", "low", ~
summary(data)
## ï..Emp_Id satisfaction_level last_evaluation number_project
## Length:14999 Length:14999 Length:14999 Min. :2.000
## Class :character Class :character Class :character 1st Qu.:3.000
## Mode :character Mode :character Mode :character Median :4.000
## Mean :3.803
## 3rd Qu.:5.000
## Max. :7.000
## average_montly_hours time_spend_company Work_accident left
## Min. : 96.0 Min. : 2.000 Min. :0.0000 Min. :0.0000
## 1st Qu.:156.0 1st Qu.: 3.000 1st Qu.:0.0000 1st Qu.:0.0000
## Median :200.0 Median : 3.000 Median :0.0000 Median :0.0000
## Mean :201.1 Mean : 3.498 Mean :0.1446 Mean :0.2381
## 3rd Qu.:245.0 3rd Qu.: 4.000 3rd Qu.:0.0000 3rd Qu.:0.0000
## Max. :310.0 Max. :10.000 Max. :1.0000 Max. :1.0000
## promotion_last_5years Department salary
## Min. :0.00000 Length:14999 Length:14999
## 1st Qu.:0.00000 Class :character Class :character
## Median :0.00000 Mode :character Mode :character
## Mean :0.02127
## 3rd Qu.:0.00000
## Max. :1.00000
Data Cleaning
data$satisfaction_level<-gsub("%","",as.character(data$satisfaction_level))
data$satisfaction_level=as.integer(data$satisfaction_level)
head(data)
data$last_evaluation<-gsub("%","",as.character(data$last_evaluation))
data$last_evaluation=as.integer(data$last_evaluation)
head(data)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.3 v stringr 1.4.0
## v tidyr 1.1.3 v forcats 0.5.1
## v readr 2.0.1
## Warning: package 'ggplot2' was built under R version 4.1.1
## Warning: package 'readr' was built under R version 4.1.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(plotly)
## Warning: package 'plotly' was built under R version 4.1.1
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggplot2)
library(dplyr)
library(plotly)
library(hrbrthemes)
## Warning: package 'hrbrthemes' was built under R version 4.1.1
## NOTE: Either Arial Narrow or Roboto Condensed fonts are required to use these themes.
## Please use hrbrthemes::import_roboto_condensed() to install Roboto Condensed and
## if Arial Narrow is not on your system, please see https://bit.ly/arialnarrow
library(highcharter)
## Warning: package 'highcharter' was built under R version 4.1.1
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(e1071)
## Warning: package 'e1071' was built under R version 4.1.1
library(caret)
## Warning: package 'caret' was built under R version 4.1.1
## Loading required package: lattice
##
## Attaching package: 'caret'
## The following object is masked from 'package:purrr':
##
## lift
library(kernlab)
## Warning: package 'kernlab' was built under R version 4.1.3
##
## Attaching package: 'kernlab'
## The following object is masked from 'package:purrr':
##
## cross
## The following object is masked from 'package:ggplot2':
##
## alpha
library(caTools)
## Warning: package 'caTools' was built under R version 4.1.3
library(randomForest)
## Warning: package 'randomForest' was built under R version 4.1.3
## randomForest 4.7-1
## Type rfNews() to see new features/changes/bug fixes.
##
## Attaching package: 'randomForest'
## The following object is masked from 'package:ggplot2':
##
## margin
## The following object is masked from 'package:dplyr':
##
## combine
df <- data
head(df)
str(df)
## 'data.frame': 14999 obs. of 11 variables:
## $ ï..Emp_Id : chr "IND02438" "IND28133" "IND07164" "IND30478" ...
## $ satisfaction_level : int 38 80 11 72 37 41 10 92 89 42 ...
## $ last_evaluation : int 53 86 88 87 52 50 77 85 100 53 ...
## $ number_project : int 2 5 7 5 2 2 6 5 5 2 ...
## $ average_montly_hours : int 157 262 272 223 159 153 247 259 224 142 ...
## $ time_spend_company : int 3 6 4 5 3 3 4 5 5 3 ...
## $ Work_accident : int 0 0 0 0 0 0 0 0 0 0 ...
## $ left : int 1 1 1 1 1 1 1 1 1 1 ...
## $ promotion_last_5years: int 0 0 0 0 0 0 0 0 0 0 ...
## $ Department : chr "sales" "sales" "sales" "sales" ...
## $ salary : chr "low" "medium" "medium" "low" ...
data <- df%>%
group_by(Department)%>%
summarize(Avg_hrs = mean(average_montly_hours))
fig <- plot_ly(data, x = ~Department, y = ~Avg_hrs, type = 'bar', color = I("dark blue"))
fig <- fig %>% layout(title = "Average monthly working hours according to department",
xaxis = list(title = "Department"),
yaxis = list(title = "Average monthly working hours"))
fig
#ggplot(df,aes(x=number_project,y=average_montly_hours))+geom_jitter(aes(color=Department))
data <- df%>%
filter(Work_accident==1)%>%
group_by(Department)%>%
summarize(No_of_wa = n())%>%
arrange(No_of_wa)
head(data)
hc <- data %>%
hchart('line', hcaes(x = Department, y = No_of_wa))%>%
hc_title(text = "Number of work accidents for each department")%>%
hc_yAxis(title = "Number of work accidents")
hc
l <- df %>% filter(salary == "low")
m <- df %>% filter(salary == "medium")
h <- df %>% filter(salary == "high")
hc2 <- hchart(
density(l$satisfaction_level), type = "area",
color = "steelblue", name = "Low Salary"
) %>%
hc_add_series(
density(m$satisfaction_level), type = "area",
color = "#B71C1C",
name = "Medium Salary"
)%>%
hc_add_series(
density(h$satisfaction_level), type = "area",
color = "yellow",
name = "High Salary"
)%>%
hc_title(text = "Density plot of satisfaction level according to salary")%>%
hc_xAxis(title = "Satisfaction Level (0-100)")
hc2
fig <- plot_ly(df, labels = ~Department, values = ~time_spend_company, type = 'pie')
fig <- fig %>% layout(title = 'Time spent per Department',
xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
fig
df2 <- df
df2$left <- as.factor(df2$left)
str(df2)
## 'data.frame': 14999 obs. of 11 variables:
## $ ï..Emp_Id : chr "IND02438" "IND28133" "IND07164" "IND30478" ...
## $ satisfaction_level : int 38 80 11 72 37 41 10 92 89 42 ...
## $ last_evaluation : int 53 86 88 87 52 50 77 85 100 53 ...
## $ number_project : int 2 5 7 5 2 2 6 5 5 2 ...
## $ average_montly_hours : int 157 262 272 223 159 153 247 259 224 142 ...
## $ time_spend_company : int 3 6 4 5 3 3 4 5 5 3 ...
## $ Work_accident : int 0 0 0 0 0 0 0 0 0 0 ...
## $ left : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
## $ promotion_last_5years: int 0 0 0 0 0 0 0 0 0 0 ...
## $ Department : chr "sales" "sales" "sales" "sales" ...
## $ salary : chr "low" "medium" "medium" "low" ...
df2$ï..Emp_Id <- NULL
split <- sample.split(df2, SplitRatio = 0.7)
split
## [1] FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE
train <- subset(df2, split == "TRUE")
test <- subset(df2, split == "FALSE")
classifier = svm(formula = left ~ .,
data = train,
type = 'C-classification',
kernel = 'linear')
y_pred = predict(classifier, newdata = test[-7])
y_train_pred = predict(classifier, newdata = train[-7])
cm = table(test[, 7], y_pred)
cm
## y_pred
## 0 1
## 0 3225 203
## 1 798 273
cm2 = table(train[, 7], y_train_pred )
cm2
## y_train_pred
## 0 1
## 0 7520 480
## 1 1859 641
# Splitting data in train and test data
# Fitting Random Forest to the train dataset
set.seed(120) # Setting seed
classifier_RF = randomForest(x = train[-7],
y = train$left,
ntree = 50)
classifier_RF
##
## Call:
## randomForest(x = train[-7], y = train$left, ntree = 50)
## Type of random forest: classification
## Number of trees: 50
## No. of variables tried at each split: 3
##
## OOB estimate of error rate: 0.88%
## Confusion matrix:
## 0 1 class.error
## 0 7982 18 0.00225
## 1 74 2426 0.02960
# Predicting the Test set results
y_pred = predict(classifier_RF, newdata = test[-7])
# Confusion Matrix
confusion_mtx = table(test[, 7], y_pred)
confusion_mtx
## y_pred
## 0 1
## 0 3417 11
## 1 78 993
# Plotting model
plot(classifier_RF)
# Importance plot
importance(classifier_RF)
## MeanDecreaseGini
## satisfaction_level 1302.277501
## last_evaluation 447.775675
## number_project 708.454623
## average_montly_hours 530.746767
## time_spend_company 697.367202
## Work_accident 21.846892
## promotion_last_5years 3.833769
## Department 42.274183
## salary 30.887432
# Variable importance plot
varImpPlot(classifier_RF)
